都道府県の表記を統一

Components/BarChart.R

@@ -106,6 +106,7 @@ output$regionTimeSeries <- renderEcharts4r({
 
 totalConfirmedByRegionData <- reactive({
   dt <- fread(paste0(DATA_PATH, 'resultSummaryTable.csv'), sep = '@')
+  dt[, region := list(fix_prefecture_str(region))]
   dt
 })
 

Components/ComfiredMap.R

@@ -2,12 +2,13 @@
 # Returns:
 #   data.table: データセット
 cumSumConfirmedByDateAndRegion <- reactive({
-  dt <- data.frame(date = byDate$date)
+  dt <- data.frame(date = byDate$date, stringsAsFactors = FALSE)
   for(i in 2:ncol(byDate)) {
-    dt[, i] = cumsum(byDate[, i, with = F])
+    dt[, i] = cumsum(byDate[, i, with = FALSE])
   }
   dt <- reshape2::melt(dt, id.vars = 'date')
-  dt <- data.table(dt)
+  dt <- data.table(dt, stringsAsFactors = FALSE)
+  dt[, variable := as.character(variable)]
   # input <- list(mapDateRange = c(as.Date('2020-03-01'), as.Date('2020-03-10')), showPopupOnMap = T) # TEST
   dt <- dt[date >= input$mapDateRange[1] & date <= input$mapDateRange[2]]
   dt
@@ -17,7 +18,7 @@ output$echartsMap <- renderEcharts4r({
   mapDt <- cumSumConfirmedByDateAndRegion()
   # mapDt <- data.table(dt) # TEST
   mapDt <- mapDt[!(variable %in% c('クルーズ船', 'チャーター便', '検疫職員'))]
-  mapDt <- merge(x = mapDt, y = provinceCode, by.x = 'variable', by.y = 'name-ja', all = T)
+  mapDt <- merge(x = mapDt, y = provinceCode, by.x = 'variable', by.y = 'name-ja', all = TRUE)
   mapDt <- mapDt[, .(date, variable, `name-en`, value)]
   colnames(mapDt) <- c('date', 'ja', 'en', 'count')
   nameMap <- as.list(mapDt$ja)

R/fix_prefecture_str.R

@@ -0,0 +1,50 @@
+is_prefecture <- function(x) {
+  sapply(x, 
+         grepl, 
+         x = "(?<=東京都|北海道|(大阪|京都)府|(青森|岩手|宮城|秋田|山形|福島|茨城|栃木|群馬|埼玉|千葉|神奈川|新潟|富山|石川|福井|山梨|長野|岐阜|静岡|愛知|三重|滋賀|兵庫|奈良|和歌山|鳥取|島根|岡山|広島|山口|徳島|香川|愛媛|高知|福岡|佐賀|長崎|熊本|大分|宮崎|鹿児島|沖縄)県)",
+         simplify = TRUE,
+         USE.NAMES = FALSE
+  )
+}
+
+fix_prefecture_str <- function(x) {
+  x %>% 
+    sapply(
+      function(x) {
+        if (is_prefecture(x)) {
+          if (grepl(x, "^京都")) {
+            "京都府"
+          } else {
+            prefecture_set <- 
+              c("北海道", "青森県", "岩手県", "宮城県", "秋田県", 
+                "山形県", "福島県", "茨城県", "栃木県", "群馬県", 
+                "埼玉県", "千葉県", "東京都", "神奈川県", "新潟県", 
+                "富山県", "石川県", "福井県", "山梨県", "長野県", 
+                "岐阜県", "静岡県", "愛知県", "三重県", "滋賀県", 
+                "京都府", "大阪府", "兵庫県", "奈良県", "和歌山県", 
+                "鳥取県", "島根県", "岡山県", "広島県", "山口県", 
+                "徳島県", "香川県", "愛媛県", "高知県", "福岡県", 
+                "佐賀県", "長崎県", "熊本県", "大分県", "宮崎県", 
+                "鹿児島県", "沖縄県")
+            str_dist <- 
+              adist(x,
+                    prefecture_set) %>% 
+              c()
+            if (length(unique(str_dist)) == 1) {
+              x
+            } else {
+              prefecture_set[which.min(str_dist)]
+            }        
+          }
+          } else {
+          x      
+        }
+      },
+      simplify = TRUE,
+      USE.NAMES = FALSE)
+}
+
+set_prefecture_fullnames <- function(data) {
+  data %>% 
+    setNames(fix_prefecture_str(names(data)))
+}

System/CreateTable.R

@@ -1,14 +1,18 @@
+library(magrittr)
 library(data.table)
 library(sparkline)
+source("R/fix_prefecture_str.R")
 
 # ====準備部分====
 DATA_PATH <- 'Data/'
 # 感染者ソーステーブルを取得
-byDate <- fread(paste0(DATA_PATH, 'byDate.csv'), header = T)
+byDate <- fread(paste0(DATA_PATH, 'byDate.csv'), header = TRUE) %>% 
+  set_prefecture_fullnames()
 byDate[is.na(byDate)] <- 0
 byDate$date <- lapply(byDate[, 1], function(x){as.Date(as.character(x), format = '%Y%m%d')})
 # 死亡データ
-death <- fread(paste0(DATA_PATH, 'death.csv'))
+death <- fread(paste0(DATA_PATH, 'death.csv')) %>% 
+  set_prefecture_fullnames()
 death[is.na(death)] <- 0
 # 国内の日報
 domesticDailyReport <- fread(paste0(DATA_PATH, 'domesticDailyReport.csv'))
@@ -35,9 +39,9 @@ langCode <- 'ja'
 # 都道府県人口密度
 provinceAttr <- fread(paste0(DATA_PATH, 'SIGNATE COVID-2019 Dataset - 都道府県マスタ.csv'))
 provinceAttr$人口 <- as.numeric(gsub(',', '', provinceAttr$人口))
-provinceAttr[, `都道府県` := gsub('県', '', `都道府県`)]
-provinceAttr[, `都道府県` := gsub('府', '', `都道府県`)]
-provinceAttr[, `都道府県` := gsub('東京都', '東京', `都道府県`)]
+# provinceAttr[, `都道府県` := gsub('県', '', `都道府県`)]
+# provinceAttr[, `都道府県` := gsub('府', '', `都道府県`)]
+# provinceAttr[, `都道府県` := gsub('東京都', '東京', `都道府県`)]
 # 色設定
 lightRed <- '#F56954'
 middleRed <- '#DD4B39'
@@ -112,9 +116,9 @@ diffSparkline <- sapply(2:ncol(byDate), function(i) {
 # 新規退院者カラム作成
 detailByRegion <- fread(paste0(DATA_PATH, 'detailByRegion.csv'))
 detailByRegion[, `日付` := as.Date(as.character(`日付`), '%Y%m%d')]
-detailByRegion[, `都道府県名` := gsub('県', '', `都道府県名`)]
-detailByRegion[, `都道府県名` := gsub('府', '', `都道府県名`)]
-detailByRegion[, `都道府県名` := gsub('東京都', '東京', `都道府県名`)]
+# detailByRegion[, `都道府県名` := gsub('県', '', `都道府県名`)]
+# detailByRegion[, `都道府県名` := gsub('府', '', `都道府県名`)]
+# detailByRegion[, `都道府県名` := gsub('東京都', '東京', `都道府県名`)]
 detailByRegion[order(`日付`), dischargedDiff := `退院者` - shift(`退院者`), by = `都道府県名`]
 detailByRegion[is.na(detailByRegion)] <- 0
 
@@ -283,13 +287,14 @@ fwrite(x = processData, file = paste0(DATA_PATH, 'resultProcessData.csv'))
 
 # =====SIGNATE データ処理=====
 provinceCode <- fread(paste0(DATA_PATH, 'prefectures.csv'))
+provinceCode[, `name-ja` := list(fix_prefecture_str(`name-ja`))]
 # svgIcon <- fread(paste0(DATA_PATH, 'svg.csv'))
 # clusterPlace<- fread(paste0(DATA_PATH, 'SIGNATE COVID-2019 Dataset - 接触場所マスタ.csv'), header = T)
 
-signateDetail<- fread(paste0(DATA_PATH, 'SIGNATE COVID-2019 Dataset - 罹患者.csv'), header = T)
-signateDetail[, 受診都道府県 := gsub('県', '', 受診都道府県)]
-signateDetail[, 受診都道府県 := gsub('府', '', 受診都道府県)]
-signateDetail[, 受診都道府県 := gsub('東京都', '東京', 受診都道府県)]
+signateDetail<- fread(paste0(DATA_PATH, '/SIGNATE COVID-2019 Dataset - 罹患者.csv'), header = T)
+# signateDetail[, 受診都道府県 := gsub('県', '', 受診都道府県)]
+# signateDetail[, 受診都道府県 := gsub('府', '', 受診都道府県)]
+# signateDetail[, 受診都道府県 := gsub('東京都', '東京', 受診都道府県)]
 signateDetail[, regionId := paste0(都道府県コード, '-', 都道府県別罹患者No)]
 
 # 年代変換

global.R

@@ -14,6 +14,7 @@ library(echarts4r)
 library(echarts4r.maps)
 library(sparkline)
 library(shinyBS)
+source("R/fix_prefecture_str.R")
 
 # ====
 # ファイルのパス設定
@@ -33,12 +34,14 @@ getFinalAndDiff <- function(vector) {
 # ====
 # データの読み込み
 # ====
-byDate <- fread(paste0(DATA_PATH, 'byDate.csv'), header = T)
+byDate <- fread(paste0(DATA_PATH, 'byDate.csv'), header = T) %>% 
+  set_prefecture_fullnames()
 byDate[is.na(byDate)] <- 0
 byDate$date <- lapply(byDate[, 1], function(x){as.Date(as.character(x), format = '%Y%m%d')})
 
 # 死亡データ
-death <- fread(paste0(DATA_PATH, 'death.csv'))
+death <- fread(paste0(DATA_PATH, 'death.csv')) %>% 
+  set_prefecture_fullnames()
 death[is.na(death)] <- 0
 
 # 行動歴データ
@@ -215,8 +218,11 @@ regionName <- as.list(regionName)
 
 
 news <- fread(paste0(DATA_PATH, 'mhlw_houdou.csv'))
+news[ , pre := list(fix_prefecture_str(pre))]
+
 
 provinceCode <- fread(paste0(DATA_PATH, 'prefectures.csv'))
+provinceCode[, `name-ja` := list(fix_prefecture_str(`name-ja`))]
 provinceSelector <- provinceCode$id
 names(provinceSelector) <- provinceCode$`name-ja`